Sony’s image sensors with built-in AI could make surveillance tech smarter

Sony has announced two new models of its intelligent vision sensors which, it claims, are the first in the world to be equipped with their own AI processing capabilities. Sony said by doing this, it enables high-speed edge AI processing, as well as reducing transmission latency, addressing privacy concerns and reducing power consumption.
While the tech giant has said that these IMX500 and IMX501 sensors could soon appear in its smartphone cameras, it also said there was significant potential in the world of the internet of things (IoT) and smart camera systems increasingly being used in retail and security.
Examples given included a smart camera at the entrance to a facility being able to count the number of people entering, or being used on a ceiling so that it can conduct heat mapping of store visitors.
Speaking with The Verge , Sony vice-president of business and innovation, Mark Hanson, said: “Now we’ve eliminated what would normally be a 60 frames per second, 4K video stream to just that one ‘hey, I recognise this object’.
“That can reduce data traffic [and] it also helps things like privacy.”
Honeywell debuts AI camera that detects rising body temperature
Staying with AI imagine, Honeywell revealed new temperature monitoring technology called ‘ThermoRebellion’. It uses thermal cameras and AI to detect elevated body temperature and can validate if an individual is wearing proper personal protective equipment (PPE).
As individuals pass in front of a high-resolution, thermal imaging camera, their skin temperature is automatically detected within two seconds and displayed on an accompanying monitor. Honeywell is piloting ThermoRebellion at two of its US production facilities, including its new N95 face mask manufacturing center in Phoenix, Arizona.
“Protecting worker safety is the top priority for any building operator and today, more than ever, managers are looking for innovative solutions to enhance their health screening processes,” said Renaud Mazarguil, president of Honeywell’s gas analysis and safety business.
“We’ve developed this breakthrough technology to automate and streamline the monitoring of an individual’s temperature and reduce the need for invasive monitoring.”
AI uses dishwasher signals to get health info
Researchers from MIT’s Computer Science and AI Laboratory (CSAIL) have developed a system called ‘ Sapple ’ that analyses in-home appliance usage to better understand our health patterns, using just radio signals and a smart electricity meter.
Sapple examines use of everyday items such as dishwashers, stoves and even hair dryers, and can detect where and when a particular appliance is being used. Of the two sensors, the ‘location sensor’ uses radio signals to sense placement, and covers an area equivalent in size to a one-bed apartment.
“This system uses passive sensing data and does not require people to change...